Game-Theoretic Motion Planning for Multi-Agent Interaction
L. Peters (TU Delft - Learning & Autonomous Control)
Javier Alonso-Mora – Promotor (TU Delft - Learning & Autonomous Control)
L. Ferranti – Promotor (TU Delft - Learning & Autonomous Control)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Robots are leaving factory floors and entering human environments, where they must move safely and efficiently while interacting with people and other autonomous systems. In these settings, decisions are interdependent: what a robot should do depends on how others will respond, and vice versa. Anticipating and shaping these responses is central to competent behavior in multi-agent settings, but it is difficult in practice because interaction unfolds under uncertainty, with limited prior knowledge of other agents’ objectives and limited sensing, and often under tight computational constraints...